Liuhan Peng
A5080794338- Advanced Image Processing Techniques
- Advanced Vision and Imaging
- Image and Signal Denoising Methods
- Image and Video Quality Assessment
- Technology Adoption and User Behaviour
- Image Processing Techniques and Applications
- Digital Marketing and Social Media
- Image Enhancement Techniques
- Blockchain Technology Applications and Security
Xinjiang University
2022-2023
University of Birmingham
2022
While blockchain is considered to have many unprecedented characteristics, and its application recognized as another new opportunity for the development of e-commerce, there limited evidence on factors affecting adoption in commercial e-commerce sector. This study aims identify determinants influencing consumers' intention adopt technology e-commerce. /methodology/approachDrawing classic acceptance model (TAM), a conceptual framework developed empirically assessed present relationships...
This paper reviews the NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video. In this challenge, we proposed LDV 2.0 dataset, which includes dataset (240 videos) 95 additional videos. challenge three tracks. Track 1 aims at enhancing videos compressed by HEVC a fixed QP. 2 3 target both super-resolution quality enhancement video. They require x2 x4 super-resolution, respectively. The tracks totally attract more than 600 registrations. test phase, 8 teams, teams...
How to use information from temporal, spatial, and frequency domain dimensions is crucial for the quality enhancement of compressed video. The state-of-the-art methods generally design powerful networks fuse spatiotemporal videos. But entire video not fully utilized effectively fused, resulting in learned context that closely related target frame. In addition, various videos have varying degrees loss. previous ignored non-uniform distortion different domains did unique algorithms domains, so...
The compressed video inevitably appears in compression artifacts, which seriously affect the Quality of Experience. state-of-the-art methods employ deformable alignment to gather similar information from multiple neighborhood frames enhance target frame quality. However, they always align simultaneously, brings repetitive and useless because imperfect alignments. In this paper, we propose a recurrent fusion method considers quality distortion caused by time distance frame. Specifically,...
This paper reviews the Challenge on Super-Resolution of Compressed Image and Video at AIM 2022. challenge includes two tracks. Track 1 aims super-resolution compressed image, Track~2 targets video. In 1, we use popular dataset DIV2K as training, validation test sets. 2, propose LDV 3.0 dataset, which contains 365 videos, including 2.0 (335 videos) 30 additional videos. this challenge, there are 12 teams 2 that submitted final results to respectively. The proposed methods solutions gauge...
This paper reviews the NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video. In this challenge, we proposed LDV 2.0 dataset, which includes dataset (240 videos) 95 additional videos. challenge three tracks. Track 1 aims at enhancing videos compressed by HEVC a fixed QP. 2 3 target both super-resolution quality enhancement video. They require x2 x4 super-resolution, respectively. The tracks totally attract more than 600 registrations. test phase, 8 teams, teams...